CN113218683A - Petroleum underground electric casing cutter fault identification method based on vibration signals - Google Patents
Petroleum underground electric casing cutter fault identification method based on vibration signals Download PDFInfo
- Publication number
- CN113218683A CN113218683A CN202110282267.4A CN202110282267A CN113218683A CN 113218683 A CN113218683 A CN 113218683A CN 202110282267 A CN202110282267 A CN 202110282267A CN 113218683 A CN113218683 A CN 113218683A
- Authority
- CN
- China
- Prior art keywords
- fault
- signal
- casing cutter
- fault identification
- vibration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000003208 petroleum Substances 0.000 title claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000005259 measurement Methods 0.000 claims abstract description 14
- 238000011084 recovery Methods 0.000 claims abstract description 12
- 238000010586 diagram Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 8
- 230000015556 catabolic process Effects 0.000 claims description 5
- 238000006731 degradation reaction Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010408 sweeping Methods 0.000 claims description 3
- 239000003129 oil well Substances 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000002474 experimental method Methods 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 239000000654 additive Substances 0.000 description 2
- 230000000996 additive effect Effects 0.000 description 2
- 238000004040 coloring Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000004873 anchoring Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013095 identification testing Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a fault identification method of an underground petroleum electric casing cutter based on vibration signals, and belongs to the technical field of fault identification. The method comprises the following steps: designing and realizing an instrument vibration state measuring device for a petroleum underground high-temperature logging environment; performing first fault characteristic recovery operation on the vibration signal by using a signal-to-noise ratio enhancement algorithm; performing a second fault feature recovery operation by using a sparse representation fast solving algorithm; converting the two-dimensional time-frequency vector after the fault characteristic is recovered into an image; forming a sample data set beta by using two-dimensional time-frequency vector graphs of different fault types, taking the sample data set beta as the input of a lightweight convolutional neural network model, and training to obtain a fault identification model; and inputting the two-dimensional time-frequency vector diagram of the unknown fault vibration signal into a fault identification model for fault identification. The method provides a whole set of fault identification solution from data measurement and characteristic recovery to fault identification, and from the test result, the method can effectively solve the fault identification problem of the petroleum underground electric casing cutter.
Description
Technical Field
The invention relates to the technical field of fault identification, in particular to a fault identification method of an underground petroleum electric casing cutter based on vibration signals.
Background
The electric casing cutter is the workover tool with the highest operation efficiency in the workover operation in the field of oilfield services. With the continuous use of the electric casing cutter in various oil fields in recent years, the failure occurrence rate is gradually increased, and the identification of the failures can save most of the cost and avoid operation accidents caused by the failures. The current fault identification method is mainly divided into three categories: (1) a fault identification method based on fault model analysis; (2) a fault identification method based on fault signal processing; (3) a fault identification method based on machine learning and deep learning. The model of the fault system of the method (1) is difficult to obtain by researchers, errors exist in the modeling process, and the problem of robustness is increasingly highlighted; the method (2) is often regarded as a detection method for detecting whether a fault occurs by researchers, and is not an effective fault identification method; the method (3) overcomes the excessive dependence of a model-based method on the model, and extracts the fault characteristics from the data. With the advent of the big data era, machine learning and deep learning become popular in the field of fault identification, but when the quality of data used for learning is poor, the features represented by the data are mostly submerged, so that the data quantity required by the machine learning and deep learning method which uses a large amount of data for model training becomes more huge, and therefore fault diagnosis by using the machine learning and the deep learning becomes challenging.
The prior art patent discloses an intelligent bearing fault diagnosis system (200810070235.2), which needs to measure six signals, wherein the first and second paths measure vibration acceleration signals, the third and fourth paths measure rotating speed signals, and the fifth and sixth paths measure rotating speed signals, and a state monitor judges the state of a bearing according to the six signals to obtain a fault identification result. However, the method requires that the tested bearing is provided with a composite sensor and cannot be popularized and used on other equipment, and the method judges the threshold value of each data through experience, depends on a large amount of priori knowledge and is poor in robustness.
In the prior art, a truck bearing fault diagnosis method [ 202011011024.9 ] based on generation countermeasure learning is disclosed, wherein vibration acceleration signals obtained through experiments are used for training through a generation countermeasure network model, then a large amount of target area data are synthesized through the generation countermeasure network after training, and then the synthesized data are used for carrying out secondary training on a convolutional neural network. According to the method, good fault identification accuracy is obtained through a large amount of training, but on one hand, the signal-to-noise ratio of data and the incompleteness of the data are not considered, and on the other hand, for the occasions with limited computing resources, the method is large in computing amount and complex in training process.
Disclosure of Invention
The invention aims to provide a method for identifying faults of an underground petroleum electric casing cutter based on vibration signals, which can effectively solve the problem of poor data quality for fault identification, can accurately extract submerged data characteristics, and directly reduces the data volume required by training due to obvious data characteristics for learning, so that the method has certain popularization.
The invention provides a petroleum underground electric casing cutter fault identification method based on vibration signals, which comprises the following steps:
s1, designing and realizing an instrument vibration state measuring device for a petroleum underground high-temperature logging environment;
s2, performing first fault characteristic recovery operation on the vibration signal by using a signal-to-noise ratio enhancement algorithm;
s3, performing secondary fault feature recovery operation by using a sparse representation fast solving algorithm;
s4, converting the two-dimensional time-frequency vector after the fault characteristic is recovered into an image;
s5, forming a sample data set beta by using two-dimensional time-frequency vector graphs of different fault types, using the sample data set beta as the input of a lightweight convolutional neural network model, and training to obtain a fault identification model;
and S6, inputting the two-dimensional time-frequency vector diagram of the unknown fault vibration signal into a fault recognition model for fault recognition.
Furthermore, the temperature of the working environment of the electric sleeve cutter is 150 ℃, and the temperature resistance value of an electronic device selected by the vibration signal measuring device is not lower than 150 ℃. The device comprises a signal measurement part and a data transmission part, wherein the signal measurement part is provided with a power supply voltage monitoring unit for providing a temperature compensation basis for a signal measurement software part, and the voltage monitoring unit is also provided with a bias current compensation module; the data transmission part is provided with an anti-interference unit, and the error code phenomenon caused by high-temperature environment on data transmission is eliminated.
Furthermore, the signal-to-noise ratio enhancement algorithm is a downhole real-time processing algorithm, the real-time performance of the algorithm shows that the enhancement matrix is calculated off-line in advance, the real-time calculation amount is greatly reduced, the dimensionality of the enhancement matrix is one-dimensional, and the complexity is low. In addition, the algorithm does not need to measure and store a large amount of data in advance during solving, and can process the data after one-time measurement is completed.
Further, the vibration signal after signal-to-noise enhancement can be approximately described by the degradation matrix H and the original signal x:
y＝Hx
obtaining the best estimate of the original signal x while solving for the degradation matrix H
I.e. a sparse representation of the original signal x containing no redundant information, the sparse representation model can be described by a non-linear optimization function:
wherein gamma isBalance xiParameters of fidelity and sparsity, and the precondition is min | | | x | |. The calculation amount of the model is huge, and in order to reduce the calculation pressure of a data processing system on the oil well, the model is quickly solved by using a quick solving algorithm.
Further, a two-dimensional time-frequency vector T is divided intoyAnd (f, n) converting the image into an image, coloring the image according to the data amplitude and the concentration to form a time-frequency distribution pseudo-color image, wherein the image can uniquely represent the fault characteristics of the petroleum underground electric casing cutter according to the concentration degree of data points in a high-frequency area, a low-frequency area and a tail sweeping area.
Further, a part (for example, 80%) of the sample data set β composed of the time-frequency distribution pseudo-color graph is used as a training set training model, and the remaining part (for example, 20%) is used as a test set testing model accuracy.
Further, the fault categories include: severe failure of blade tooth breakage, failure of blade integral breakage and failure of casing cutter anchor eccentricity.
In summary, the technical effects of the technical solution conceived by the present invention are as follows:
(1) the method can be used for recovering the fault characteristics of the petroleum underground electric casing cutter, effectively solves the problem of poor data quality for fault identification, can accurately extract the submerged data characteristics, and the energy point diagram formed after the characteristic recovery can uniquely represent the fault characteristics of the petroleum underground electric casing cutter according to the concentration degree of the energy points in the high-frequency area, the low-frequency area and the tail-sweeping area.
(2) The method can be used for identifying the fault characteristics of the petroleum underground electric casing cutter, and can be used for training a model with higher accuracy by using less data volume and shorter time and combining a light convolutional neural network structure due to obvious data characteristics used for learning, so that the data volume required by training is directly reduced.
Description of the drawings:
FIG. 1 is a flow chart of a method according to the present invention;
FIG. 2 is a system block diagram of the high temperature resistant vibration signal measuring apparatus according to the present invention;
FIG. 3 is a diagram of the results of fault identification according to the present invention;
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in FIG. 1, the invention provides a fault identification method of an oil downhole electric casing cutter based on vibration signals, which comprises the following steps:
s1, designing and realizing an instrument vibration state measuring device for a petroleum underground high-temperature logging environment;
the signal measurement module in the device finishes the acquisition of vibration signals, and because the supply voltage of the vibration signal measurement component under the high-temperature environment is easy to be unstable, and the output of the signal measurement module fluctuates correspondingly, the signal measurement module is provided with a voltage monitoring unit and can provide a temperature compensation basis for a software program of the signal measurement module. In order to prevent error code phenomenon in data transmission caused by high temperature, the data transmission module is provided with an anti-interference unit which is mainly composed of transient suppression diodes.
S2, performing first fault characteristic recovery operation on the vibration signal by using a signal-to-noise ratio enhancement algorithm;
the vibration measurement signal y can be described by a linear combination of the degradation matrix H, the raw signal x and the additive noise v:
y＝Hx+v
to recover x from y, we first want to remove the additive noise v, a process described by the signal-to-noise enhancement:
the signal-to-noise ratio enhancement process is as follows: (1) performing one-step prediction on the current vibration acceleration data to obtain a predicted value; (2) calculating a deviation of such prediction; (3) combining the current measured value, the algorithm predicted value and the enhancement matrix to obtain a signal-to-noise ratio enhancement value closest to the true value of the current vibration data; (4) updating the deviation; and repeating the process after the next vibration acceleration data measurement is carried out. And in the next signal-to-noise ratio enhancement process, the last signal-to-noise ratio enhancement value is used as the current one-step prediction value.
S3, performing secondary fault feature recovery operation by using a sparse representation fast solving algorithm;
the sparse representation fast solving algorithm process is as follows: the data after signal-to-noise ratio enhancement is y'n＝{y′1，y′2，y′3，...y′nAnd the quick solving process of the sparse representation model comprises the following steps: (1) will y'nDecomposing into a continuous signal having a plurality of components; (2) calculating a fast solving transformation coefficient; (3) calculating the instantaneous frequency f of the combination of the transform amplitude and step sizes(ii) a (4) Computing a two-dimensional time-frequency vector Ty(f，n)。
S4, converting the two-dimensional time-frequency vector after the fault characteristics are recovered into an image;
using Matlab to treat TyAnd (f, n) drawing an image and performing coloring treatment to generate a time-frequency distribution pseudo-color graph which can uniquely represent the fault characteristics of the petroleum underground electric casing cutter.
S5, forming a sample data set beta by using the characteristic images of different fault types, wherein the sample data set beta is used as the input of a lightweight convolutional neural network model, and training to obtain a fault identification model;
one part (for example, 80%) of a sample data set beta composed of the feature images is used as a training set to train the model, the other part (for example, 20%) is used as a test set to test the accuracy of the model, and the parameters and the structure of the model are adjusted to achieve the ideal condition.
And S6, inputting the two-dimensional time-frequency vector diagram of the vibration signal into a fault recognition model for fault recognition.
Experimental examples:
1. experimental procedures and experimental instructions:
for verificationEffectiveness of a method for identifying faults of an underground petroleum electric casing cutter based on vibration signals, wherein a high-temperature environment vibration signal measuring device shown in figure 2 is used for collecting vibration signals y for different faults of the casing cutter respectivelyi(t), i represents a state type including: y is1(t) is in a normal state, y2(t) blade tooth breakage catastrophic failure condition, y3(t) failure State of Overall breakage of blade and y4(t) a cannula cutter anchoring eccentric fault condition. The experimental procedures will be described in detail below:
carrying out first fault characteristic recovery operation on the acquired fault vibration signal y (t) by using a signal-to-noise ratio enhancement algorithm to obtain y' (t); and performing secondary fault feature recovery operation on y' (T) by using a sparse representation fast solving algorithm to obtain Ty(f, n); will Ty(f, n) converting the vector graph into a two-dimensional time-frequency vector graph; for y1(t) Normal State, y2(t) blade tooth breakage catastrophic failure, y3(t) failure of the blade to break in its entirety and y4(T) vibration signature of casing cutter anchored eccentric fault the above steps are performed, with T of the 4's different statesy(f, n) the converted image constitutes a sample data set β. Training is performed using a sample data set β as input to the lightweight convolutional neural network, with 80% of the total number of each failure sample as the training set and the remaining 20% as the test set. And identifying the vibration signal of the casing cutter with unknown fault by using the fault identification model of the petroleum underground electric casing cutter, and judging the fault type.
2. And (3) fault identification experiment results:
FIG. 3 is a fault identification test result diagram, and it can be seen from the fault identification experiment result that the fault identification of the high-temperature downhole electric casing cutter can be effectively realized by using the method.
Claims (7)
1. A fault identification method for an oil underground electric casing cutter based on vibration signals is characterized by comprising the following steps:
s1, designing and realizing an instrument vibration state measuring device for a petroleum underground high-temperature logging environment;
s2, performing first fault characteristic recovery operation on the vibration signal by using a signal-to-noise ratio enhancement algorithm;
s3, performing secondary fault feature recovery operation by using a sparse representation fast solving algorithm;
s4, converting the two-dimensional time-frequency vector after the fault characteristic is recovered into an image;
s5, forming a sample data set beta by using two-dimensional time-frequency vector graphs of different fault types, using the sample data set beta as the input of a lightweight convolutional neural network model, and training to obtain a fault identification model;
and S6, inputting the two-dimensional time-frequency vector diagram of the unknown fault vibration signal into a fault recognition model for fault recognition.
2. The method for identifying the fault of the downhole motor casing cutter based on the vibration signal as claimed in claim 1, wherein the step S1 is specifically that the temperature of the working environment of the motor casing cutter is 150 ℃, and the temperature resistance value of the electronic device selected by the vibration signal measuring device is not lower than 150 ℃. The device comprises a signal measurement part and a data transmission part, wherein the signal measurement part is provided with a power supply voltage monitoring unit for providing a temperature compensation basis for a signal measurement software part, and the voltage monitoring unit is also provided with a bias current compensation module; the data transmission part is provided with an anti-interference unit, and the error code phenomenon caused by high-temperature environment on data transmission is eliminated.
3. The method for identifying the fault of the downhole motor-driven casing cutter based on the vibration signal as claimed in claim 1, wherein the step S2 is specifically as follows:
the signal-to-noise ratio enhancement algorithm is a downhole real-time processing algorithm, the real-time performance of the algorithm shows that an enhancement matrix is calculated off-line in advance, the real-time calculation amount is greatly reduced, the dimension of the enhancement matrix is one-dimensional, and the complexity is low. In addition, the algorithm does not need to measure and store a large amount of data in advance during solving, and can process the data after one-time measurement is completed.
4. The method for identifying the fault of the downhole motor-driven casing cutter based on the vibration signal as claimed in claim 1, wherein the step S3 is specifically as follows:
the signal-to-noise enhanced vibration signal can be approximately described by the degradation matrix H and the original signal x: y is Hx
Obtaining the best estimate of the original signal x while solving for the degradation matrix H
I.e. a sparse representation of the original signal x containing no redundant information, the sparse representation model can be described by a non-linear optimization function:
wherein gamma is a parameter for balancing the fidelity and sparsity of xi, and min | | | x | | is a precondition. In order to reduce the computational pressure of the oil well data processing system, the model is quickly solved by adopting a quick solving algorithm.
5. The method for identifying the fault of the downhole petroleum electric casing cutter based on the vibration signal as claimed in claim 1, wherein the step S4 is specifically to convert the two-dimensional time-frequency vector Ty (f, n) into an image, and color the image according to the data amplitude and concentration to form a time-frequency distribution pseudo-color graph, wherein the image can uniquely represent the fault characteristics of the downhole petroleum electric casing cutter according to the concentration degree of data points in the high-frequency region, the low-frequency region and the tail-sweeping region.
6. The method for identifying the fault of the downhole motor-driven casing cutter based on the vibration signal as claimed in claim 1, wherein the step S5 is to combine the time-frequency distribution pseudo-color image into a sample data set β, use a part of the data set β as a training set training model, and use the remaining part as a test set to test the model accuracy.
7. The method for identifying faults of an oil downhole electric casing cutter based on vibration signals as claimed in claim 1, wherein the fault category comprises: blade tooth breakage failure, blade integrity failure, and casing cutter anchor eccentricity failure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110282267.4A CN113218683A (en) | 2021-03-16 | 2021-03-16 | Petroleum underground electric casing cutter fault identification method based on vibration signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110282267.4A CN113218683A (en) | 2021-03-16 | 2021-03-16 | Petroleum underground electric casing cutter fault identification method based on vibration signals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113218683A true CN113218683A (en) | 2021-08-06 |
Family
ID=77083736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110282267.4A Pending CN113218683A (en) | 2021-03-16 | 2021-03-16 | Petroleum underground electric casing cutter fault identification method based on vibration signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113218683A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115526218A (en) * | 2022-11-29 | 2022-12-27 | 科瑞工业自动化***（苏州）有限公司 | Train wheel set tread morphology on-line monitoring method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5210798A (en) * | 1990-07-19 | 1993-05-11 | Litton Systems, Inc. | Vector neural network for low signal-to-noise ratio detection of a target |
| CN105447243A (en) * | 2015-11-17 | 2016-03-30 | 中国计量学院 | Weak signal detection method based on adaptive fractional order stochastic resonance system |
| CN105738109A (en) * | 2016-02-22 | 2016-07-06 | 重庆大学 | Bearing fault classification diagnosis method based on sparse representation and ensemble learning |
| CN106408087A (en) * | 2016-09-18 | 2017-02-15 | 厦门大学 | Reinforcement learning adaptive stochastic resonance method for underwater weak signal detection |
| CN112326017A (en) * | 2020-09-28 | 2021-02-05 | 南京航空航天大学 | Weak signal detection method based on improved semi-classical signal analysis |
-
2021
- 2021-03-16 CN CN202110282267.4A patent/CN113218683A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5210798A (en) * | 1990-07-19 | 1993-05-11 | Litton Systems, Inc. | Vector neural network for low signal-to-noise ratio detection of a target |
| CN105447243A (en) * | 2015-11-17 | 2016-03-30 | 中国计量学院 | Weak signal detection method based on adaptive fractional order stochastic resonance system |
| CN105738109A (en) * | 2016-02-22 | 2016-07-06 | 重庆大学 | Bearing fault classification diagnosis method based on sparse representation and ensemble learning |
| CN106408087A (en) * | 2016-09-18 | 2017-02-15 | 厦门大学 | Reinforcement learning adaptive stochastic resonance method for underwater weak signal detection |
| CN112326017A (en) * | 2020-09-28 | 2021-02-05 | 南京航空航天大学 | Weak signal detection method based on improved semi-classical signal analysis |
Non-Patent Citations (2)
| Title |
|---|
| VARUNJAIN: "Vibration monitoring of ball nose end mill tool during milling of sculptured surfaces using MUP6050 sensor", 《MATERIALS TODAY: PROCEEDINGS》 * |
| 王春雷等: "一种基于深度学习的电机轴承故障诊断方法", 《兰州交通大学学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115526218A (en) * | 2022-11-29 | 2022-12-27 | 科瑞工业自动化***（苏州）有限公司 | Train wheel set tread morphology on-line monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tao et al. | Bearings fault detection using wavelet transform and generalized Gaussian density modeling | |
| CN109489977B (en) | KNN-AdaBoost-based bearing fault diagnosis method | |
| Zheng et al. | Research on rolling bearing fault diagnosis of small dataset based on a new optimal transfer learning network | |
| CN113485302B (en) | Vehicle operation process fault diagnosis method and system based on multivariate time sequence data | |
| CN112200244A (en) | Intelligent detection method for anomaly of aerospace engine based on hierarchical countermeasure training | |
| CN112182490B (en) | Reactor state diagnosis method and system | |
| CN112326213A (en) | Abnormal data detection method and device and mechanical fault detection method and device | |
| CN114263621B (en) | Test method and system for centrifugal pump cavitation fault diagnosis simulation | |
| CN114354184A (en) | Deep learning-based method and device for establishing health early warning model of main shaft of large-scale rotating equipment | |
| Li et al. | Intelligent fault diagnosis of aeroengine sensors using improved pattern gradient spectrum entropy | |
| CN112200060A (en) | Network model-based rotating equipment fault diagnosis method and system and readable storage medium | |
| Lu et al. | Early fault warning and identification in condition monitoring of bearing via wavelet packet decomposition coupled with graph | |
| CN113218683A (en) | Petroleum underground electric casing cutter fault identification method based on vibration signals | |
| CN114741945A (en) | Diagnosis method for online faults of aircraft engine | |
| CN112880726A (en) | Sensor fault diagnosis method and device based on variational modal decomposition sample entropy | |
| CN115962944A (en) | VMD-based real-time diagnosis method for bearing fault of cutting part of intelligent coal mining machine group | |
| Qi et al. | A new deep fusion network for automatic mechanical fault feature learning | |
| CN114662977A (en) | Method and system for detecting abnormity of motion state of offshore drilling platform and electronic equipment | |
| CN115099264A (en) | Ship part fault diagnosis method and device, computer and computer storage medium | |
| CN109506936B (en) | Bearing fault degree identification method based on flow chart and non-naive Bayes inference | |
| CN113642101B (en) | Fault diagnosis method and device for hydraulic power steering gear | |
| CN112834194B (en) | Fault intelligent detection method based on soft target measurement under fault-free sample | |
| CN112653158B (en) | Frequency response characteristic identification method for doubly-fed wind power plant with additional frequency control | |
| CN116610941B (en) | Method, system, equipment and medium for diagnosing composite fault of bearing of rapid kurtosis graph | |
| CN117688496B (en) | Abnormality diagnosis method, system and equipment for satellite telemetry multidimensional time sequence data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210806 |